This metadata record describes outputs from 12 configurations of long short-term memory (LSTM) models which were used to predict streamflow drought occurrence at 384 stream gage locations in the Colorado River Basin region. The models were trained on data from 01-Oct-1981 to 31-Mar-2005 and validated over the period of record spanning 01-Apr-2005 to 31-Mar- 2014. The models use explanatory variable inputs described in Wieczorek (2023) (doi.org/10.5066/P98IG8LO) to predict daily streamflow and streamflow percentiles as described in Simeone (2022) (doi.org/10.5066/P92FAASD). Separate models were trained to predict daily streamflow and streamflow percentiles. Two types of percentiles were modeled: (1) fixed-threshold percentiles that are based on comparing all streamflow throughout the year, and (2) variable-threshold percentiles that compare streamflow separately for each day of the year (using a moving 30-day window). Separate models were trained for predicting at lead times of 0, 7 and 14 days ahead. Details on methods and model configurations can be found in Hamshaw and others (2023). The comma separated files are grouped by target variables and lead times as listed in the table below and include model output for the validation period (01-Apr-2005 to 31-Mar-2014). This metadata record also includes model code (see Readme.txt within the CRB_NN_model_archive.zip for more details) and a model performance metrics file (model_validation_performance_metrics_by_gage.csv). <table border="1" cellpadding="1" cellspacing="1" style="width:700px"> <caption>Model configurations included in the data release. PUB refers to "Predictions in Ungaged Basins" model configuration and Q refers to streamflow.</caption> <thead> <tr> <th scope="col">Data File</th> <th scope="col">Prediction target variable</th> <th scope="col">Forecast lead time</th> <th scope="col">Model Configurations</th> </tr> </thead> <tbody> <tr> <td>streamflow_model_predictions_0day_ahead.csv</td> <td>Daily Streamflow (mm/day)</td> <td>0 days</td> <td> <p>Streamflow-0d,&nbsp;</p> <p>PUB-Streamflow-0d</p> </td> </tr> <tr> <td>streamflow_model_predictions_7day_ahead.csv</td> <td>Daily Streamflow (mm/day)</td> <td>7 days</td> <td> <p>Streamflow-7d</p> </td> </tr> <tr> <td>streamflow_model_predictions_14day_ahead.csv</td> <td>Daily Streamflow (mm/day)</td> <td>14 days</td> <td>Streamflow-14d</td> </tr> <tr> <td>percentile_fixed_model_predictions_0day_ahead.csv</td> <td>Fixed Percentile</td> <td>0 days</td> <td> <p>Fixed-0d,</p> <p>PUB-Fixed-0d</p> <p>Q-to-Fixed-0d</p> </td> </tr> <tr> <td>percentile_fixed_model_predictions_7day_ahead.csv</td> <td>Fixed Percentile</td> <td>7 days</td> <td>Fixed-7d</td> </tr> <tr> <td>percentile_fixed_model_predictions_14day_ahead.csv</td> <td>Fixed Percentile</td> <td>14 days</td> <td>Fixed-14d</td> </tr> <tr> <td>percentile_variable_model_predictions_0day_ahead.csv</td> <td>Variable Percentile</td> <td>0 days</td> <td> <p>Variable-0d,</p> <p>PUB-Variable-0d,</p> <p>Q-to-Variable-0d</p> </td> </tr> <tr> <td>percentile_variable_model_predictions_7day_ahead.csv</td> <td>Variable Percentile</td> <td>7 days</td> <td>Variable-7d</td> </tr> <tr> <td>percentile_variable_model_predictions_14day_ahead.csv</td> <td>Variable Percentile</td> <td>14 days</td> <td>Variable-14d</td> </tr> </tbody> </table>